This paper introduces SPLATT, a C library with shared-memory parallelism for three-mode tensors. SPLATT contains algorithmic improvements over competing state ...

Two sparse matrix-vector multiplications per column. Requires an auxiliary sparse matrix with as many nonzeros as there are non-empty fibers.

This paper introduces SPLATT, a C library with shared-memory parallelism for three-mode tensors. SPLATT contains algorithmic improvements over competing state ...

SPLATT has a fast, parallel method of multiplying a matricide tensor by a Khatri-Rao product, which is a key kernel in tensor factorization methods.

This paper introduces SPLATT, a C library with shared-memory parallelism for three-mode tensors. SPLATT contains algorithmic improvements over competing state ...

SPLATT uses a novel data structure that exploits the sparsity patterns of tensors. This data structure has a small memory footprint similar to competing methods ...

IPDPS 2015 : 2015 IEEE 29th International Parallel and Distributed Processing Symposium : proceedings : 25-29 May 2015, Hyderabad, India / , 2015, p.19-70 ,.

SPLATT: Efficient and parallel sparse tensor-matrix multiplication. S Smith, N Ravindran, ND Sidiropoulos, G Karypis. 2015 IEEE International Parallel and ...

SPLATT: Efficient and parallel sparse tensor-matrix multiplication. In International Parallel & Distributed Processing Symposium (IPDPS'15), 2015.

Technical Report. 2019. • SPLATT: Efficient and parallel sparse tensor-matrix multiplication. Shaden Smith, Niranjay Ravindran, Nicholas D Sidiropoulos, and ...